Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2618 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.6300. Min Act: -0.1700
Data Index: 2440913 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5988. Min Act: -0.1700
Data Index: 2430113 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.6300. Min Act: -0.1700
Data Index: 6932750 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 5142185 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5988. Min Act: -0.1700
Data Index: 1415005 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 2882404 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 345457 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 2466450 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 5264387 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 6348632 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 1722765 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 6824745 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 1758616 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 6830174 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5363. Min Act: -0.1700
Data Index: 6886893 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 2036156 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 1115536 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 7484413 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 7830316 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6300. Min Range: -6.6300
Max Act: 6.5675. Min Act: -0.1700
Data Index: 219076 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19